Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Video completion using tracking and fragment merging

Jia, Yun-Tao, Hu, Shi-Min and Martin, Ralph Robert 2005. Video completion using tracking and fragment merging. The Visual Computer 21 (8-10) , pp. 601-610. 10.1007/s00371-005-0313-3

[img]
Preview
PDF
Download (453kB) | Preview

Abstract

Video completion is the problem of automatically filling space–time holes in video sequences left by the removal of unwanted objects in a scene. We solve it using texture synthesis, filling a hole inwards using three steps iteratively: we select the most promising target pixel at the edge of the hole, we find the source fragment most similar to the known part of the target’s neighborhood, and we merge source and target fragments to complete the target neighborhood, reducing the size of the hole. Earlier methods were slow, due to searching the whole video data for source fragments or completing holes pixel by pixel; they also produced blurred results due to sampling and smoothing. For speed, we track moving objects, allowing us to use a much smaller search space when seeking source fragments; we also complete holes fragment by fragment instead of pixelwise. Fine details are maintained by use of a graph cut algorithm when merging source and target fragments. Further techniques ensure temporal consistency of hole filling over successive frames. Examples demonstrate the effectiveness of our method

Item Type: Article
Date Type: Publication
Status: Published
Schools: Computer Science & Informatics
Subjects: Q Science > QA Mathematics > QA76 Computer software
Uncontrolled Keywords: Video completion; Texture synthesis; Mean shift; Graph cut; Tracking
Additional Information: PDF uploaded in accordance with publisher's policy http://www.springer.com/gp/open-access/authors-rights/self-archiving-policy/2124 [accessed 27/01/2015]
Publisher: Springer
ISSN: 0178-2789
Last Modified: 04 Jun 2017 05:45
URI: http://orca.cf.ac.uk/id/eprint/43160

Citation Data

Cited 83 times in Google Scholar. View in Google Scholar

Cited 63 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item Edit Item

Downloads

Downloads per month over past year

View more statistics